CVE-2026-34070
LangChain is a framework for building agents and LLM-powered applications. Prior to version 1.2.22, multiple functions in langchain_core.pro
CVSS
7.5
High
EPSS
1.2%
p65
KEV
—
Exploit Today
19
0-100
Published: Mar 31, 2026 · Last modified: Jul 15, 2026 · CWE-22
LangChain is a framework for building agents and LLM-powered applications. Prior to version 1.2.22, multiple functions in langchain_core.prompts.loading read files from paths embedded in deserialized config dicts without validating against directory traversal or absolute path injection. When an application passes user-influenced prompt configurations to load_prompt() or load_prompt_from_config(), an attacker can read arbitrary files on the host filesystem, constrained only by file-extension checks (.txt for templates, .json/.yaml for examples). This issue has been patched in version 1.2.22.
- github.comhttps://github.com/langchain-ai/langchain/commit/27add913474e01e33bededf4096151130ba0d47c
- github.comhttps://github.com/langchain-ai/langchain/releases/tag/langchain-core==1.2.22
- github.comhttps://github.com/langchain-ai/langchain/security/advisories/GHSA-qh6h-p6c9-ff54
- access.redhat.comhttps://access.redhat.com/errata/RHSA-2026:24766
- access.redhat.comhttps://access.redhat.com/errata/RHSA-2026:37275
- access.redhat.comhttps://access.redhat.com/security/cve/CVE-2026-34070
- bugzilla.redhat.comhttps://bugzilla.redhat.com/show_bug.cgi?id=2453287
- github.comhttps://github.com/langchain-ai/langchain/security/advisories/GHSA-qh6h-p6c9-ff54
- security.access.redhat.comhttps://security.access.redhat.com/data/csaf/v2/vex/2026/cve-2026-34070.json